Morph Apply

This is a speed optimization for editing large files you haven't read yet. Instead of burning tokens to read a 1000 line file just to add three lines of error handling, you pass a code snippet with markers like "// ... existing code ..." and let Morph's API figure out where it goes. Processes at 10,500 tokens per second with 98% accuracy. The tradeoff is obvious: you need the MCP server configured and you're trusting the API to place your edit correctly, but when you're working with big files or doing batch edits where you know the context, it beats reading the whole thing into Claude first.